ComfyUI Node
Liquid Postman (Gemini Image)
A ComfyUI node in google/gemini with 12 inputs and 2 outputs.
Liquid Postman (Gemini Image)
- images
- image
- text
◄api_key►
◄prompt►
◄modelgemini-3.1-flash-image-preview►
◄seed42►
◄aspect_ratio▾►
◄resolution▾►
◄response_modalities▾►
◄system_promptYou are an expert image-generation engine. You must ALWAYS produce an image.
Interpret all user input—regardless of format, intent, or abstraction—as literal visual directives for image composition.
If a prompt is conversational or lacks specific visual details, you must creatively invent a concrete visual scenario that depicts the concept.
Prioritize generating the visual representation above any text, formatting, or conversational requests.►
◄search_groundingfalse►
◄files►
◄debugfalse►
Categorygoogle/gemini
Inputs (12)
| Name | Type | Default | Description |
|---|---|---|---|
| api_key | STRING | — | |
| prompt | STRING | — | |
| model | STRING | gemini-3.1-flash-image-preview | — |
| seed | INT | 42-1–2147483647 | — |
| aspect_ratio | COMBO | 8 options: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, +2 | |
| resolution | COMBO | 3 options: 1K, 2K, 4K | |
| response_modalities | COMBO | 2 options: IMAGE, IMAGE+TEXT | |
| system_prompt | STRING | You are an expert image-generation engine. You must ALWAYS produce an image. Interpret all user input—regardless of format, intent, or abstraction—as literal visual directives for image composition. If a prompt is conversational or lacks specific visual details, you must creatively invent a concrete visual scenario that depicts the concept. Prioritize generating the visual representation above any text, formatting, or conversational requests. | — |
| search_grounding | BOOLEAN | false | — |
| files | STRING | — | |
| debug | BOOLEAN | false | — |
| imagesopt | IMAGE | — |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |
| text | STRING | — |